Security
7,153 rows, by stacks then stars
772 of these skill files have been read, by 666 distinct authors, and what they tell an agent counted. What Security authors agree on, and what they forbid
Ghosteken/agent-harness/skills/api-security-best-practices Skill
1★ repoImplement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/api-security-testing Skill
1★ repoAPI security testing workflow for REST and GraphQL APIs covering authentication, authorization, rate limiting, input validation, and security best practices.
Ghosteken/agent-harness/skills/attack-tree-construction Skill
1★ repoBuild comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
The same file is in 7 other repositories
Ghosteken/agent-harness/skills/backend-security-coder Skill
1★ repoExpert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
Ghosteken/agent-harness/skills/broken-authentication Skill
1★ repoIdentify and exploit authentication and session management vulnerabilities in web applications. Broken authentication consistently ranks in the OWASP Top 10 and can lead to account takeover, identity theft, and unauthorized access to sensitive systems.
Ghosteken/agent-harness/skills/container-security-hardening Skill
1★ repoProduction-grade engineering skills and specialist agent personas for AI coding assistants. Orchestrates the full SDLC, from spec to ship, with structured verification gates, anti-rationalization checks, and senior-level engineering discipline.
Ghosteken/agent-harness/skills/docker-expert Skill
1★ repoProduction-grade engineering skills and specialist agent personas for AI coding assistants. Orchestrates the full SDLC, from spec to ship, with structured verification gates, anti-rationalization checks, and senior-level engineering discipline.
Ghosteken/agent-harness/skills/frontend-security-coder Skill
1★ repoExpert in secure frontend coding practices specializing in XSS prevention, output sanitization, and client-side security patterns.
The same file is in 7 other repositories
Ghosteken/agent-harness/skills/gha-security-review Skill
1★ repoFind exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.
The same file is in 5 other repositories
Ghosteken/agent-harness/skills/secrets-management Skill
1★ repoSecure secrets management practices for CI/CD pipelines using Vault, AWS Secrets Manager, and other tools.
Ghosteken/agent-harness/skills/security-and-hardening Skill
1★ repoHardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
The same file is in 2 other repositories
Security requirement extraction
Ghosteken/agent-harness/skills/security-requirement-extraction Skill
1★ repoDerive security requirements from threat models and business context. Use when translating threats into actionable requirements, creating security user stories, or building security test cases.
The same file is in 4 other repositories
Security scanning security dependencies
Ghosteken/agent-harness/skills/security-scanning-security-dependencies Skill
1★ repoYou are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies.
The same file is in 3 other repositories
Security scanning security hardening
Ghosteken/agent-harness/skills/security-scanning-security-hardening Skill
1★ repoCoordinate multi-layer security scanning and hardening across application, infrastructure, and compliance controls.
The same file is in 3 other repositories
Security scanning security sast
Ghosteken/agent-harness/skills/security-scanning-security-sast Skill
1★ repo'Static Application Security Testing (SAST) for code vulnerability
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/threat-modeling-expert Skill
1★ repoExpert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use PROACTIVELY for security architecture reviews, threat identification, or building secure-by-design systems.
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/top-web-vulnerabilities Skill
1★ repoProvide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category. This skill enables systematic vulnerability identification, impact assessment, and remediation guidance across the full spectrum of web security threats.
The same file is in 5 other repositories
Ghosteken/agent-harness/skills/vulnerability-scanner Skill
1★ repoAdvanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/web-security-testing Skill
1★ repoWeb application security testing workflow for OWASP Top 10 vulnerabilities including injection, XSS, authentication flaws, and access control issues.
batur/ts-baseline-docs/.agents/skills/security-baseline Skill
1★ repoEnforce the project's secure-by-default TypeScript/Node.js security baseline. Use when creating or reviewing authentication, authorization, API endpoints, input handling, CORS, rate limits, secrets, logging, webhooks, file uploads, SSRF-sensitive URL fetching, dependency/security checks, or AI-generated code.
yiyaw-lab/agent-armor/vault Skill
1★ repoPrompt vault plus pre-enrichment policy. Save high-value reusable prompts, preserve the original, write a stronger reusable version, add trigger metadata for future retrieval, and decide when broad prompts should be pre-enriched before implementation. Modes: save | enrich | fire | list.
ofoxai/skills/skills/hal-vault Skill
1★ repoSecurely store, search, and use secrets (API keys, tokens, passwords, SSH keys) with hal-vault, an SSH-key encrypted local secret store. Use when the user shares a credential that should be saved, asks what secrets are stored or where a key is, or when a command/workflow needs a secret injected. Core discipline - never print raw secret values into chat, logs, or files; reference secrets only by their masked form, and use --reveal exclusively inside command substitution.
impactbrussels/AINativeOS/skills/red-team-the-agent Skill
1★ repoUse when an agent is about to meet real users or an auditor and you need to attack it first, the way a hostile user or a security reviewer would. Reach for this when you say "try to break it", "can someone jailbreak this", "is it injection-safe", "what if a user lies to it", "the agent has tools and I am scared", "prove it is hard to abuse", or before a launch, a pen test, or a security questionnaire. Distinct from eval-and-safety-harness, which builds the general eval substrate and guardrails: this is the offensive, adversarial attack suite and the loop that runs against them. Produces a red-team attack suite (categories plus concrete attacks), a severity x exploitability scoring rubric, and a pass/fail release gate wired before ship. Invoke after eval-and-safety-harness, before design-the-mva.
impactbrussels/AINativeOS/skills/secure-the-connectors Skill
1★ repoUse when an agent is about to get tools or connectors and you need to bound what it can actually do, the way a security reviewer would before granting access. Reach for this when you say "should I connect this MCP server", "what can my agent reach", "is this tool safe to expose", "it has access to our data now", "tool poisoning", "least privilege for agents", or before wiring any connector that can read private data or take an irreversible action. Distinct from red-team-the-agent, which attacks the running agent: this hardens the connector and tool-supply-chain layer before an attack ever lands. Produces a connector-risk register, a least-privilege scope map, an approval flow for destructive tools, and a connector entry in the scheduled permission re-audit. Invoke after architect-before-code, alongside eval-and-safety-harness and red-team-the-agent.
celestialdust/achilles-skills/skills/code-simplification Skill
1★ repoReduce code complexity without changing behavior — the Review-stage QUALITY axis. Use the moment a slice's code is green but reads heavier than it should: deep nesting, nested ternaries, dead code, generic names, copy-paste duplication, speculative abstractions. Apply Chesterton's Fence (understand before you cut) and stay scoped to what changed. Quality only — it does NOT hunt for bugs (that is `code-review`/`security-and-hardening`). It NEVER edits tests or changes behavior; if a simplification cannot be made without touching behavior, it HALTS instead of weakening the gate.
celestialdust/achilles-skills/skills/security-and-hardening Skill
1★ repoAudits a code diff for security vulnerabilities before it can ship. MUST run as a fresh, code-cold reviewer on every Implement diff in the Review fan-out — and any time code touches user input, auth, sessions, secrets, data storage, external/URL fetches, file uploads, or LLM output. A CRITICAL/HIGH finding or a secret in the diff is a hard STOP: the slice is halted, never opened as a PR.
motao123/dev-workflow-kit/security-review Skill
1★ repoUse when a change affects trust boundaries such as authentication, authorization, untrusted input, secrets, or sensitive data handling. This skill identifies security risks, abuse cases, and verification steps without replacing implementation review.
codexskills/agent-forge/skills/security-and-hardening Skill
no license1★ repoSystematic application of security controls across the entire software development lifecycle. Covers OWASP Top 10 prevention, authentication patterns, secrets management, dependency auditing, input validation, and a three-tier security boundary system that enforces defense in depth.
shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/security-and-hardening Skill
1★ repoHardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
The same file is in 8 other repositories
zcccc-mxc/codex-skill-router/examples/skills/security-review Skill
1★ repoUse when reviewing authentication, authorization, login permissions, access control, API security, and bypass risks. Do not use for visual layout, image generation, deployment, or documentation-only tasks.
LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/security-checklist Skill
1★ repoA pattern → severity → fix checklist for reviewing security-sensitive code (auth, payments, user input, file uploads, webhooks). Use as the LLM-reasoning complement to a deterministic SAST scan — semgrep catches known patterns, this catches the contextual ones. Run on any diff touching a trust boundary.
LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/semgrep Skill
1★ repoRun static analysis (SAST) over the codebase with semgrep to find real bug and security patterns — injection, auth gaps, secret handling, dangerous APIs. Use before a security-sensitive PR, on auth/payment/data-handling code, or when the user asks for a deterministic security scan.
jimtin/production-ai/skills/codebase-prune-review Skill
1★ repoReview an existing codebase for redundant, legacy, dead, superseded, or attack-surface-increasing code paths and guide progressive removal with behavior mapping, test coverage, security review, and validation. Use when asked to remove old providers or integrations, clean redundant code paths, reduce tech debt, reduce attack surface, review dead code, retire obsolete routes, remove stale compatibility layers, or clean up after migrations such as Google Drive uploads to Vercel Blob.
jimtin/production-ai/skills/security-threat-model Skill
1★ repoEvidence-grounded threat modeling for a repository, subsystem, or automation. Builds a system model from the actual code, derives trust boundaries and assets, enumerates realistic abuse paths with likelihood/impact priorities, and writes a reviewable Markdown threat model. Use when asked to threat model a codebase or path, enumerate threats or abuse paths, assess attack surface, or when another skill escalates security-sensitive scope (auth, uploads, parsers, webhooks, payments, secrets, admin paths, deployment, CI/CD) before push-readiness. Do not use for generic code review, compliance paperwork, or non-security design discussion.
sumitaich1998/slavex/.cursor/skills/power-stride Skill
1★ repoStrides forward fast and aggressively with long powerful steps, a forward lean and pumping bent arms, TRANSLATING via moveTo while the engine drives the legs. Use when a command mentions power stride, stride out, march hard, powerful walk, drive forward, or big strong steps.
sumitaich1998/slavex/.cursor/skills/vault-onto Skill
1★ repoVaults the character energetically up onto a surface to stand on it. Use when the user says vault onto the table, leap up onto that, or jump up and stand on a surface.
sumitaich1998/slavex/.cursor/skills/vault Skill
1★ repoVaults over an obstacle by planting the hands and swinging the legs over to one side, via a sequence with a root.y arc and forward translation. Use when a command mentions vault, vault over, hands-on vault, kong vault, or hop over by pushing off your hands.
vecten/sdlc-toolkit/skills/triage-security Skill
1★ repoTriage security advisories (CVEs, breach notices, dependency vulnerabilities) against the workspace stack, draft a Slack response stating whether the project is affected, and hand off follow-up work to the create-ticket skill. Use when the user says "triage security", "security advisory", "security news", "check security brief", or provides a Slack permalink, CVE ID, or pasted advisory text.
Security assurance operations review
SylphxAI/skills/skills/security-assurance-operations-review Skill
1★ repoPrepare or audit one truthful customer security-assurance packet and its claim-evidence operating loop across questionnaires, procurement responses, trust-center content, gated reports, control mappings, gaps, exceptions, commitments, freshness, access, and revocation. Use when the primary artifact is what the company may say and prove about current security. Do not use for security implementation, threat modeling, penetration testing, vulnerability remediation, incident response, compliance audit execution, or contract redlining.
SylphxAI/skills/skills/security-threat-modeling Skill
1★ repoModel security threats for a new or materially changed system, architecture, trust boundary, data flow, integration, privileged action, or deployment, and produce a Threat Model and Security Design Contract. Use when security objectives, attack surfaces, abuse cases, controls, and residual risk must shape design before or during implementation. Do not use for product-wide fraud or incentive abuse, customer assurance claims, penetration-test execution, isolated vulnerability remediation, compliance attestation, or incident response.
Paldom/github-skills/skills/repo-protections Skill
1★ repoConfigures GitHub repository protections - rulesets (require PR, required checks, no force pushes), secret scanning and push protection, Dependabot, private vulnerability reporting, and Actions hardening. Use when the user asks to protect a branch, set up branch protection or rulesets, enable security features, or harden a repo. Not for writing SECURITY.md or fixing code vulnerabilities.
notwld/engineering-baseline/skills/security-review Skill
1★ repoPerform mandatory feature-level threat modeling and security verification using STRIDE, OWASP ASVS 5.0.0 Level 2, OWASP Top 10:2025, NIST CSF 2.0, and NIST SP 800-207 Zero Trust. Use for every new feature and material behavior change, and for reviews involving authentication, authorization, trust boundaries, APIs, untrusted input, sensitive data, secrets, cryptography, files, external URLs, dependencies, infrastructure, logging, or deployment. State mitigations before implementation and verify controls afterward.
ksed8/cc-loopkit/.claude/skills/security Skill
1★ repoSecurity audits and threat modeling — find and reason about vulnerabilities in auth, input handling, data access, secrets, and dependencies. Use when reviewing code for security, threat-modeling a feature, hardening an endpoint, handling auth/authz, or checking for injection, secret leakage, or unsafe data exposure. For a focused review of the current diff, prefer the `/security-review` command.
bglglzd/agent-workflows/plugins/agent-workflows/skills/security-red-team-audit Skill
1★ repoRun an authorized, safety-bounded red-team security assessment of an application, API, website, mobile client, or service, then fix verified weaknesses with regression tests. Use when Codex must review auth, access control, input handling, rate limits, Burp Suite findings, secrets, dependencies, infrastructure, or abuse paths without testing unapproved targets.
Deadlymind/nanolama/skills/ai-integration Skill
1★ repoWires Anthropic Claude into a Django/DRF backend — the agentic tool-use loop (model proposes tool_use, app runs it, returns tool_result, repeat), a write-tool safety contract for data-mutating tools, capability limits against prompt injection, an OCR/structured-extraction pipeline validated against a schema before persist, Tavily search, and per-tenant metering. Use when adding a Claude agent or tool loop, exposing a tool that mutates data, doing document OCR extraction, calling the anthropic SDK, choosing a model id, or capping AI spend per tenant. Not for regression-testing agent behaviour, golden sets or LLM-as-judge scoring (see ai-evals), the Celery worker that runs a long call (see celery-tasks), or auditing a tool's blast radius (see security-review).
Deadlymind/nanolama/skills/code-review Skill
1★ repoReviews the current git diff across four lenses (correctness, simplification, reuse, efficiency) and emits findings ranked by severity with file—line and a concrete failure scenario, plus nanolama-specific gates a generic reviewer misses (missing entreprise tenant filter, fail-closed regression, resource_action RBAC gap on a custom @action, DRF N+1, TanStack Query cache-key/invalidation bugs). Use when reviewing a diff or PR, doing a self-review before pushing, or asked to "review my changes" or "look over this diff". Not for exploit-focused auth/injection review (see security-review), query-plan/load profiling (see perf-review), or proving the change runs (see verify).
Deadlymind/nanolama/skills/security-review Skill
1★ repoAudits a diff for this stack's top risks — tenant isolation on every business queryset (fail-closed, no client-supplied tenant id trusted), RBAC on every custom endpoint and @action, PII leakage in list endpoints/logs/exports, file-upload validation (content-type, size, extension, private storage), and secrets not committed. Use when reviewing a Django/DRF change before merge, auditing a new ViewSet or upload handler, checking a PR for security issues, or asked "is this safe to ship". Findings are confidence-gated. Run only on TRUSTED diffs — not hardened against prompt injection. Not for generic correctness/quality review (see code-review) or proving behavior works (see verify).
Deadlymind/nanolama/skills/threat-modeling Skill
1★ repoRuns design-time STRIDE threat modelling on a feature before the code exists — names the trust boundaries this stack actually has (the tenant boundary, RBAC roles inside a tenant, the auth cookie and CSRF edge, file-upload ingestion, inbound webhooks and third-party payloads, and the AI tool surface where a model-supplied argument is attacker-influenced input), walks spoofing, tampering, repudiation, information disclosure, denial of service and elevation of privilege against only the boundaries the feature crosses, then emits a short threat-to-mitigation-to-owning-skill table of work items. Use when designing a new endpoint or background job, introducing a new trust boundary or a new class of data, planning anything that touches money, PII or auth, writing an RFC or ADR, or asked "what could go wrong with this design". Not for auditing an existing diff (see security-review) or reacting after a breach or outage (see incident-response).
alidevai/chiron_agent/.claude/skills/mcp-security-review Skill
no license1★ repoBir MCP sunucusunu veya tool'u sisteme baglamadan once guvenlik acisindan denetleme prosedurudur. MCP sunuculari dosya sistemi, terminal, e-posta, GitHub, veritabani veya broker gibi yuksek yetkili kaynaklara erisebildigi icin baglanti oncesi zorunlu incelemedir.
alidevai/chiron_agent/.claude/skills/secure-capability-acquisition Skill
no license1★ repoEksik bir skill/MCP/tool'u guvenli sekilde edinme prosedurunun tam akisi. "Hemen bulup kur" yerine "hemen arastir, hemen sandbox'a al, hemen test et, risk uygunsa ekle; degilse onay iste veya reddet" ilkesini uygular. Yeni bir yetenek kurulmasi gerektiginde kullanilir.
RudrenduPaul/skillguard/examples/skill-set-cross-privilege/vault-reader Skill
1★ repoA synthetic fixture skill bundled with SkillGuard's SG09 (cross-skill privilege chaining) tests. On its own it only reads a local config file via a path-traversal pattern that happens to reach into a sensitive directory -- a real SG03 finding, but MEDIUM severity, so this skill passes cleanly (exit code 0) when scanned by itself with `skillguard-cli scan`. It is inert: no real filesystem or network calls. Do not install or run this in a real agent.
yigityildiz0/universal-ai-skill-library/skills/common/advanced-attack-patterns Skill
no license1★ repoAdvanced attack classes beyond the OWASP Top 10 baseline including state desynchronization, cache poisoning, replay attacks, and timing-attack side.
yigityildiz0/universal-ai-skill-library/skills/common/cve-reachability-analyzer Skill
no license1★ repoDetermine whether a CVE in a dependency actually affects your application by tracing call paths from your code to vulnerable functions, analyzing transitive.
yigityildiz0/universal-ai-skill-library/skills/common/dependency-security-audit Skill
no license1★ repoAudit project dependencies for known vulnerabilities (CVEs), license issues, and outdated packages with SBOM generation. Use when deploying to production.
Firebase security rules auditor
yigityildiz0/universal-ai-skill-library/skills/common/firebase-security-rules-auditor Skill
no license1★ repoA skill to evaluate how secure Firestore security rules are. Use this when Firestore security rules are updated to ensure that the generated rules are.
yigityildiz0/universal-ai-skill-library/skills/common/operational-risk-assessment Skill
no license1★ repoIdentify, score, prioritize, and monitor operational risks with owners, controls, scenarios, and residual uncertainty. Use for risk assessment, risk register, operational risk, mitigation plan, or contingency planning.
yigityildiz0/universal-ai-skill-library/skills/common/security-and-hardening Skill
no license1★ repoHardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature.
yigityildiz0/universal-ai-skill-library/skills/common/security-auditor Skill
no license1★ repoAudits code for security vulnerabilities, exposed secrets, and unsafe patterns. Use when asked to "security audit", "check for vulnerabilities", "is this.
yigityildiz0/universal-ai-skill-library/skills/common/security-best-practices Skill
no license1★ repoPerform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security.
yigityildiz0/universal-ai-skill-library/skills/common/security-ownership-map Skill
no license1★ repoAnalyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for.